LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving

• URL: http://arxiv.org/abs/2603.01928v1
• Date: Mon, 02 Mar 2026 14:42:36 GMT
• Title: LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving
• Authors: Yuechen Luo, Fang Li, Shaoqing Xu, Yang Ji, Zehan Zhang, Bing Wang, Yuannan Shen, Jianwei Cui, Long Chen, Guang Chen, Hangjun Ye, Zhi-Xin Yang, Fuxi Wen,
• Abstract summary: Vision-Language-Action (VLA) models have revolutionized autonomous driving by unifying perception and planning.<n>Their reliance on explicit textual Chain-of-Thought (CoT) leads to semantic-perceptual decoupling and perceptual-symbolic conflicts.<n>Recent shifts toward latent reasoning attempt to bypass these bottlenecks by thinking in continuous hidden space.
• Score: 21.38662345656532
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While Vision-Language-Action (VLA) models have revolutionized autonomous driving by unifying perception and planning, their reliance on explicit textual Chain-of-Thought (CoT) leads to semantic-perceptual decoupling and perceptual-symbolic conflicts. Recent shifts toward latent reasoning attempt to bypass these bottlenecks by thinking in continuous hidden space. However, without explicit intermediate constraints, standard latent CoT often operates as a physics-agnostic representation. To address this, we propose the Latent Spatio-Temporal VLA (LaST-VLA), a framework shifting the reasoning paradigm from discrete symbolic processing into a physically grounded Latent Spatio-Temporal CoT. By implementing a dual-feature alignment mechanism, we distill geometric constraints from 3D foundation models and dynamic foresight from world models directly into the latent space. Coupled with a progressive SFT training strategy that transitions from feature alignment to trajectory generation, and refined via Reinforcement Learning with Group Relative Policy Optimization (GRPO) to ensure safety and rule compliance. \method~setting a new record on NAVSIM v1 (91.3 PDMS) and NAVSIM v2 (87.1 EPDMS), while excelling in spatial-temporal reasoning on SURDS and NuDynamics benchmarks.

Related papers

• VLMFusionOcc3D: VLM Assisted Multi-Modal 3D Semantic Occupancy Prediction [0.0]
  VLMFusionOcc3D is a robust multimodal framework for dense 3D semantic occupancy prediction in autonomous driving.<n>We introduce Weather-Aware Adaptive Fusion, a dynamic gating mechanism that utilizes vehicle metadata and weather-conditioned prompts to re-weight sensor contributions.<n>Our approach achieves significant improvements in challenging weather scenarios, offering a scalable and robust solution for complex urban navigation.
  arXiv  Detail & Related papers  (2026-03-03T05:22:28Z)
• OmniVL-Guard: Towards Unified Vision-Language Forgery Detection and Grounding via Balanced RL [63.388513841293616]
  Existing forgery detection methods fail to handle the interleaved text, images, and videos prevalent in real-world misinformation.<n>To bridge this gap, this paper targets to develop a unified framework for omnibus vision-language forgery detection and grounding.<n>We propose textbf OmniVL-Guard, a balanced reinforcement learning framework for omnibus vision-language forgery detection and grounding.
  arXiv  Detail & Related papers  (2026-02-11T09:41:36Z)
• HiST-VLA: A Hierarchical Spatio-Temporal Vision-Language-Action Model for End-to-End Autonomous Driving [20.266736153749417]
  Vision-Language-Action (VLA) models offer promising capabilities for autonomous driving through multimodal understanding.<n>Their utilization in safety-critical scenarios is constrained by inherent limitations, including numerical reasoning, weak 3D spatial awareness, and high sensitivity to context.<n>We propose HiST-VLA, a novel Hierarchical Spatio-Temporal VLA model designed for reliable trajectory generation.
  arXiv  Detail & Related papers  (2026-02-11T07:08:33Z)
• RSGround-R1: Rethinking Remote Sensing Visual Grounding through Spatial Reasoning [61.84363374647606]
  Remote Sensing Visual Grounding (RSVG) aims to localize target objects in large-scale aerial imagery based on natural language descriptions.<n>These descriptions often rely heavily on positional cues, posing unique challenges for Multimodal Large Language Models (MLLMs) in spatial reasoning.<n>We propose a reasoning-guided, position-aware post-training framework, dubbed textbfRSGround-R1, to progressively enhance spatial understanding.
  arXiv  Detail & Related papers  (2026-01-29T12:35:57Z)
• SGDrive: Scene-to-Goal Hierarchical World Cognition for Autonomous Driving [52.02379432801349]
  We propose SGDrive, a novel framework that structures the VLM's representation learning around driving-specific knowledge hierarchies.<n>Built upon a pre-trained VLM backbone, SGDrive decomposes driving understanding into a scene-agent-goal hierarchy that mirrors human driving cognition.
  arXiv  Detail & Related papers  (2026-01-09T08:55:42Z)
• ColaVLA: Leveraging Cognitive Latent Reasoning for Hierarchical Parallel Trajectory Planning in Autonomous Driving [44.008287454538596]
  Vision-language models (VLMs) enrich this paradigm by introducing cross-modal priors and commonsense reasoning.<n>Current VLM-based planners face three key challenges: (i) a mismatch between discrete text reasoning and continuous control, (ii) high latency from autoregressive chain-of-thought decoding, and (iii) inefficient or non-causal planners that limit real-time deployment.<n>We propose ColaVLA, a unified vision-language-action framework that transfers reasoning from text to a unified latent space and couples it with a hierarchical, parallel trajectory decoder.
  arXiv  Detail & Related papers  (2025-12-28T14:06:37Z)
• TrackVLA++: Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Tracking [30.955088934475928]
  We present TrackVLA++, a novel model that enhances embodied visual tracking with two key modules, a spatial reasoning mechanism and atemporal Identification Memory (TIM)<n>TrackVLA++ achieves state-of-the-art performance on public benchmarks across both egocentric and multi-camera settings.
  arXiv  Detail & Related papers  (2025-10-08T15:29:17Z)
• Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving [55.13109926181247]
  We introduce ReflectDrive, a learning-based framework that integrates a reflection mechanism for safe trajectory generation via discrete diffusion.<n>Central to our approach is a safety-aware reflection mechanism that performs iterative self-correction without gradient.<n>Our method begins with goal-conditioned trajectory generation to model multi-modal driving behaviors.
  arXiv  Detail & Related papers  (2025-09-24T13:35:15Z)
• FlowDrive: Energy Flow Field for End-to-End Autonomous Driving [50.89871153094958]
  FlowDrive is a novel framework that introduces physically interpretable energy-based flow fields to encode semantic priors and safety cues into the BEV space.<n> Experiments on the NAVSIM v2 benchmark demonstrate that FlowDrive achieves state-of-the-art performance with anS of 86.3, surpassing prior baselines in both safety and planning quality.
  arXiv  Detail & Related papers  (2025-09-17T13:51:33Z)
• ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving [49.07731497951963]
  ReCogDrive is a novel Reinforced Cognitive framework for end-to-end autonomous driving.<n>We introduce a hierarchical data pipeline that mimics the sequential cognitive process of human drivers.<n>We then address the language-action mismatch by injecting the VLM's learned driving priors into a diffusion planner.
  arXiv  Detail & Related papers  (2025-06-09T03:14:04Z)
• FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving [19.81442567260658]
  We propose a visual-temporalT framework that enables VLAs to think in images.<n>On nuScenes and NAVSIM, FSDrive improves accuracy and reduces collisions.
  arXiv  Detail & Related papers  (2025-05-23T09:55:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.